GoEnhance APIGoEnhance API
Overview

MiniMax H3 Reference to Video API

MiniMax H3 reference to video takes your own images as the reference for a new clip — characters, products, scenes — and returns 5 to 15 seconds of video with native stereo audio. Up to 6 reference images can travel with a single request, numbered in your prompt as <Picture 1> through <Picture 6>.

On the GoEnhance Open API it is the hailuo_h3_refs model on the same REST endpoint as the rest of the video catalogue. This endpoint runs on GoEnhance's own GPU cluster, so its tiers are 480p, 720p and 2K — the same self-hosted pricing as the standard MiniMax H3 endpoint.

Prefer a visual editor over writing code? Try MiniMax H3 Reference to Video on goenhance.ai.

Specifications
Modes
Reference to video
Reference inputs
Up to 6 reference images
Duration
5–15s
Resolution
480p · 720p · 2K
Aspect ratio
16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 3:2 · 2:3
Audio
Native stereo audio
Prompt
Up to 7,000 characters
Endpoint
POST /api/v1/videos/generations
Price
$0.030 / sec
Frequently asked questions
What can I use as a reference?

Up to 6 images in one request, passed as ref_imgs. The array order defines the numbering, so <Picture 1> in your prompt refers to the first URL. Video and audio references are no longer accepted on this endpoint.

How long can the output be?

Any whole number of seconds from 5 to 15, the same as the other MiniMax H3 endpoint. Requests without a duration default to 5 seconds.

Can I combine references with a first and last frame?

No. Frame control and reference material are mutually exclusive, which is why GoEnhance exposes them as two endpoints: use hailuo_h3 for first/last frame, and this model for reference-driven generation.

What does it cost?

It is billed per second of output, by resolution — see the pricing table on this page. 2K renders at 720p first and is then upscaled, so it takes longer. You are charged once per task at submission, and refunded in full if generation fails.